© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118796
    Prev
    Next
    INDEX
    Explanations

    words following a period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -2.08
     our
    -1.41
     hierdie
    -1.38
     tohoto
    -1.30
     hierv
    -1.18
     we
    -1.16
     هذا
    -1.16
     ایشان
    -1.14
     these
    -1.14
     ceci
    -1.13
    POSITIVE LOGITS
     that
    1.63
     etwa
    1.59
     about
    1.53
    That
    1.52
     But
    1.47
     That
    1.43
    But
    1.41
     but
    1.39
    About
    1.31
     officials
    1.29
    Activations Density 0.069%

    No Known Activations